modelscope / KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech
☆483Updated 8 months ago
Related projects: ⓘ
- 基于标贝数据继续训练,同时对原本的FastSpeech2模型做了改进,引入了韵律表征以及韵律预测模块,使中文发音更生动且富有节奏☆234Updated last year
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆367Updated 3 months ago
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,146Updated 7 months ago
- 商用级开源语音自动识别程序库,开箱即用,全平台支持,中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide a s…☆491Updated 4 months ago
- chinese speech pretrained models☆1,004Updated 3 weeks ago
- 这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆482Updated last year
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆163Updated 3 months ago
- Text Normalization & Inverse Text Normalization☆445Updated 2 weeks ago
- A 10000+ hours dataset for Chinese speech recognition☆490Updated last year
- Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei …☆460Updated 2 years ago
- ☆463Updated 3 months ago
- Unoffical implementation of Megatts2☆255Updated 5 months ago
- The dataset of Speech Recognition☆382Updated 2 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆436Updated last month
- Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine. 中英语音识别、多角色语音合成,支持多语言,准确率高☆458Updated 6 months ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆813Updated 2 months ago
- It is a multi-lingual (97 languages) text content automatic recognition and segmentation tool. 强大的TTS多语言(97种语言)混合文本内容自动分词工具。☆90Updated last week
- Chinese voice corpus. 中文语音语料,语音更加清晰自然,包含8个开源数据集,3200个说话人,900小时语音,1300万字。☆574Updated 4 years ago
- 基于PyTorch的VITS-BigVGAN的tts中文模型,加入韵律预测模型。☆192Updated 2 years ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆426Updated last week
- 第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验,同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。☆519Updated last year
- 中文标点符号模型,可以给文本添加标点符号。☆128Updated 6 months ago
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆516Updated last year
- VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design☆461Updated last year
- TTS appalication based on modelscope KAN-TTS☆43Updated 5 months ago
- unofficial vits2-TTS implementation in pytorch☆472Updated 5 months ago
- FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion☆588Updated 5 months ago
- 一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1☆460Updated last year
- 一个快速制作语音数据集的可视化工具☆190Updated 6 months ago
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型,同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆213Updated 2 weeks ago